RunningHubAPI

LLM Models

Get API key
Base URL · OpenAI compatible
https://llm.runninghub.ai/v1

Use an enterprise shared API key · Capabilities vary by model

  • openai/gpt-6-astra-saver
    65% off
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$10$3.5
    >272K$20$7
    Output
    ≤272K$50$17.5
    >272K$75$26.25
    Cache pricing
    Cache hit$0.35

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-6-sol
    Standard
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$2
    >272K$4
    Output
    ≤272K$10
    >272K$15
    Cache pricing
    Cache hit$0.2

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.6-sol-saver
    65% off
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$4$1.4
    >272K$8$2.8
    Output
    ≤272K$20$7
    >272K$30$10.5
    Cache pricing
    Cache hit$0.14

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.6-terra-saver
    65% off
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$2$0.7
    >272K$4$1.4
    Output
    ≤272K$12$4.2
    >272K$18$6.3
    Cache pricing
    Cache hit$0.07

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.5-saver
    65% off
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$5$1.75
    >272K$10$3.5
    Output
    ≤272K$30$10.5
    >272K$45$15.75
    Cache pricing
    Cache hit$0.175

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-6-luna
    Standard
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$0.1
    >272K$0.2
    Output
    ≤272K$0.5
    >272K$0.75
    Cache pricing
    Cache hit$0.01

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.7-flash
    50% off
    Standard
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.75$0.375
    Output
    All tokens$3.75$1.875
    Cache pricing
    Cache hit$0.0375

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.6-luna-saver
    65% off
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$0.2$0.07
    >272K$0.4$0.14
    Output
    ≤272K$1.2$0.42
    >272K$1.8$0.63
    Cache pricing
    Cache hit$0.007

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.1-flash-lite-preview
    50% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.25$0.125
    Output
    All tokens$1.5$0.75
    Cache pricing
    Cache hit$0.0125

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.5-flash
    50% off
    Standard
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.5$0.75
    Output
    All tokens$9$4.5
    Cache pricing
    Cache hit$0.075

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.5-pro
    Standard
    ChatToolsVisionStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$30
    >272K$60
    Output
    ≤272K$180
    >272K$270
    Cache pricing
    Cache hit$3

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • qwen/qwen3.8-flash-next
    Standard
    ChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.118
    Output
    All tokens$0.398
    Cache pricing
    Cache hit$0.015

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • deepseek/deepseek-v4.1-flash
    40% off
    标准版
    ChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.295$0.177
    Output
    All tokens$1.177$0.7062
    Cache pricing
    Cache hit$0.0036

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-fable-5-1
    20% off
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$10$8
    Output
    All tokens$50$40
    Cache pricing
    5m write$10
    1h write$16
    Cache hit$0.2

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5.3-flash
    Standard
    ChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.15
    Output
    All tokens$0.5
    Cache pricing
    Cache hit$0.03

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-fable-5
    20% off
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$10$8
    Output
    All tokens$50$40
    Cache pricing
    5m write$10
    1h write$16
    Cache hit$0.8

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • deepseek/deepseek-v4-flash-vision-exp
    Standard
    ChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.295
    Output
    All tokens$1.177
    Cache pricing
    Cache hit$0.006

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.4-pro
    Standard
    ChatToolsStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$30
    >272K$60
    Output
    ≤272K$180
    >272K$270
    Cache pricing
    Cache hit$3

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5.3
    10% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.177$1.0593
    Output
    All tokens$4.118$3.7062
    Cache pricing
    Cache hit$0.2655

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-opus-5
    20% off
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$5$4
    Output
    All tokens$25$20
    Cache pricing
    5m write$5
    1h write$8
    Cache hit$0.4

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-opus-4.8-saver
    80% off
    ChatToolsVisionStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$5$1
    Output
    All tokens$25$5
    Cache pricing
    5m write$1.25
    1h write$2
    Cache hit$0.1

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-opus-4.7-saver
    80% off
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$5$1
    Output
    All tokens$25$5
    Cache pricing
    5m write$1.25
    1h write$2
    Cache hit$0.1

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5.2
    35% off
    Standard
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.177$0.76505
    Output
    All tokens$4.118$2.6767
    Cache pricing
    1h write$0
    Cache hit$0.19175

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-opus-4.6-saver
    80% off
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$5$1
    Output
    All tokens$25$5
    Cache pricing
    5m write$1.25
    1h write$2
    Cache hit$0.1

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.4
    Standard
    ChatToolsStreaming
    Context1050000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤272K$2.5
    >272K$5
    Output
    ≤272K$15
    >272K$22.5
    Cache pricing
    Cache hit$0.25

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.3-codex
    Standard
    ChatToolsStreaming
    Context400000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.75
    Output
    All tokens$14
    Cache pricing
    Cache hit$0.175

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5.1
    Standard
    ChatToolsStreaming
    Context200K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32.768K$0.883
    >32.768K$1.177
    Output
    ≤32.768K$3.53
    >32.768K$4.118
  • glm/glm-5-turbo
    Standard
    ChatToolsStreaming
    Context200K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32.768K$0.736
    >32.768K$1.03
    Output
    ≤32.768K$3.236
    >32.768K$3.824
  • qwen/qwen3.8-max
    Standard
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.765
    Output
    All tokens$5.295
    Cache pricing
    5m write$2.206
    Cache hit$0.221

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-sonnet-4.6-saver
    80% off
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$3$0.6
    Output
    All tokens$15$3
    Cache pricing
    5m write$0.75
    1h write$1.2
    Cache hit$0.06

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5
    Standard
    ChatToolsStreaming
    Context200K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32.768K$0.589
    >32.768K$0.883
    Output
    ≤32.768K$2.648
    >32.768K$3.236
  • anthropic/claude-sonnet-5
    20% off
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$2$1.6
    Output
    All tokens$10$8
    Cache pricing
    5m write$2
    1h write$3.2
    Cache hit$0.16

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • qwen/qwen3.7-max
    Standard
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.765
    Output
    All tokens$5.295
    Cache pricing
    5m write$2.206
    Cache hit$0.221

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • glm/glm-5v-turbo
    Standard
    ChatToolsVisionStreaming
    Context200K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32.768K$0.736
    >32.768K$1.03
    Output
    ≤32.768K$3.236
    >32.768K$3.824
  • qwen/qwen3.7-plus
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤256K$0.295
    256K-1M$0.883
    Output
    ≤256K$1.177
    256K-1M$3.53
    Cache pricing
    5m write$0.368
    Cache hit$0.03

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • deepseek/deepseek-v4-pro
    55% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.324$0.5958
    Output
    All tokens$3.971$1.78695
    Cache pricing
    1h write$0
    Cache hit$0.02025

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • xai/grok-4.7
    15% off
    Standard
    ChatToolsVisionStreaming
    Context500000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤199.999K$2$1.7
    >199.999K$4$3.4
    Output
    ≤199.999K$6$5.1
    >199.999K$12$10.2
    Cache pricing
    Cache hit$0.425

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • xai/grok-4.6
    15% off
    Standard
    ChatToolsVisionStreaming
    Context500000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤199.999K$2$1.7
    >199.999K$4$3.4
    Output
    ≤199.999K$6$5.1
    >199.999K$12$10.2
    Cache pricing
    Cache hit$0.425

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • xai/grok-4.5
    15% off
    Standard
    ChatToolsVisionStreaming
    Context500000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$2$1.7
    Output
    All tokens$6$5.1
    Cache pricing
    Cache hit$0.425

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • xai/grok-4.3
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤204.8K$1.25
    >204.8K$2.5
    Output
    ≤204.8K$2.5
    >204.8K$5
  • qwen/qwen3.6-plus
    Standard
    ChatToolsVisionStreaming
    Context1000000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤256K$0.295
    256K-1M$1.177
    Output
    ≤256K$1.765
    256K-1M$7.059
    Cache pricing
    5m write$0.368
    Cache hit$0.03

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.1-pro-preview
    50% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤200K$2$1
    >200K$4$2
    Output
    ≤200K$12$6
    >200K$18$9
    Cache pricing
    Cache hit$0.1

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • moonshotai/kimi-k3
    15% off
    Standard
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$3.01261$2.56072
    Output
    All tokens$15.05894$12.8001
    Cache pricing
    Cache hit$0.25677

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • bytedance/doubao-seed-evolving
    30% off
    Standard
    Official web searchChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.883$0.6181
    Output
    All tokens$4.412$3.0884
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

    Cache pricing
    1h write$0.0021
    Cache hit$0.1239

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • bytedance/doubao-seed-2.1-pro
    30% off
    Standard
    Official web searchChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.883$0.6181
    Output
    All tokens$4.412$3.0884
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

    Cache pricing
    1h write$0.0021
    Cache hit$0.1239

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-sonnet-4.5
    20% off
    Standard
    ChatToolsStreaming
    Context1000000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$3$2.4
    Output
    All tokens$15$12
    Cache pricing
    5m write$3
    1h write$4.8
    Cache hit$0.24

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • bytedance/doubao-seed-2.1-turbo
    30% off
    Standard
    Official web searchChatToolsVisionStreaming
    Context256K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.442$0.3094
    Output
    All tokens$2.206$1.5442
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

    Cache pricing
    1h write$0.0021
    Cache hit$0.0623

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • anthropic/claude-opus-4.5
    20% off
    Standard
    ChatToolsStreaming
    Context200000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$5$4
    Output
    All tokens$25$20
    Cache pricing
    5m write$5
    1h write$8
    Cache hit$0.4

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • bytedance/doubao-seed-2.0-pro
    15% off
    Standard
    Official web searchChatVisionStreaming
    Context256K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32K$0.471$0.40035
    32K-128K$0.706$0.6001
    128K-256K$1.412$1.2002
    Output
    ≤32K$2.353$2.00005
    32K-128K$3.53$3.0005
    128K-256K$7.059$6.00015
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

  • bytedance/doubao-seed-2.0-code
    15% off
    Standard
    Official web searchChatToolsStreaming
    Context256K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32K$0.471$0.40035
    32K-128K$0.706$0.6001
    128K-256K$1.412$1.2002
    Output
    ≤32K$2.353$2.00005
    32K-128K$3.53$3.0005
    128K-256K$7.059$6.00015
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

  • deepseek/deepseek-v4-flash
    55% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.442$0.1989
    Output
    All tokens$1.324$0.5958
    Cache pricing
    1h write$0
    Cache hit$0.00675

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • qwen/qwen3.6-flash
    Standard
    ChatToolsStreaming
    Context1000000 tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤256K$0.177
    256K-1M$0.706
    Output
    ≤256K$1.059
    256K-1M$4.236
    Cache pricing
    5m write$0.221
    Cache hit$0.018

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.4-mini
    Standard
    ChatToolsStreaming
    Context400000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.75
    Output
    All tokens$4.5
    Cache pricing
    Cache hit$0.075

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • openai/gpt-5.4-nano
    Standard
    ChatToolsStreaming
    Context400000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.2
    Output
    All tokens$1.25
    Cache pricing
    Cache hit$0.02

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3-flash-preview
    50% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.5$0.25
    Output
    All tokens$3$1.5
    Cache pricing
    Cache hit$0.025

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-2.5-flash
    50% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.3$0.15
    Output
    All tokens$2.5$1.25
    Cache pricing
    Cache hit$0.015

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • bytedance/doubao-seed-2.0-lite
    15% off
    Standard
    Official web searchChatVisionStreaming
    Context256K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32K$0.089$0.07565
    32K-128K$0.133$0.11305
    128K-256K$0.265$0.22525
    Output
    ≤32K$0.53$0.4505
    32K-128K$0.795$0.67575
    128K-256K$1.589$1.35065
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

  • bytedance/doubao-seed-2.0-mini
    15% off
    Standard
    Official web searchChatVisionStreaming
    Context256K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤32K$0.03$0.0255
    32K-128K$0.059$0.05015
    128K-256K$0.118$0.1003
    Output
    ≤32K$0.295$0.25075
    32K-128K$0.589$0.50065
    128K-256K$1.177$1.00045
    Official web searchAdditional fee
    Web search0.55556 USD / 1,000 uses
    Toutiao0.83333 USD / 1,000 uses
    Douyin0.83333 USD / 1,000 uses
    Moji Weather0.83333 USD / 1,000 uses

    Billed by actual source usage. One answer may use multiple resources. The estimate is not a spending cap.

  • minimax/minimax-m2.7
    Standard
    ChatToolsStreaming
    Context200K tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.309
    Output
    All tokens$1.236
  • anthropic/claude-haiku-4.5-saver
    80% off
    ChatToolsStreaming
    Context200000 tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1$0.2
    Output
    All tokens$5$1
    Cache pricing
    5m write$0.25
    1h write$0.4
    Cache hit$0.02

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • qwen/qwen3.6-max-preview
    Standard
    ChatToolsStreaming
    Context250K tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤128K$1.324
    128K-256K$2.206
    Output
    ≤128K$7.942
    128K-256K$13.236
    Cache pricing
    5m write$1.655
    Cache hit$0.133

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-2.5-pro
    50% off
    Standard
    ChatToolsStreaming
    Context1M tokens
    The input-token tier determines both input and output unit prices.
    Price unit：USD / 1M tokens
    Input
    ≤200K$1.25$0.625
    >200K$2.5$1.25
    Output
    ≤200K$10$5
    >200K$15$7.5
    Cache pricing
    Cache hit$0.0625

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.5-flash-lite-saver
    80% off
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.3$0.06
    Output
    All tokens$2.5$0.5
    Cache pricing
    Cache hit$0.006

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.6-flash
    50% off
    Standard
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$1.5$0.75
    Output
    All tokens$7.5$3.75
    Cache pricing
    Cache hit$0.075

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.

  • google/gemini-3.8-flash
    50% off
    Standard
    ChatToolsVisionStreaming
    Context1M tokens
    Price unit：USD / 1M tokens
    Input
    All tokens$0.75$0.375
    Output
    All tokens$3.75$1.875
    Cache pricing
    Cache hit$0.0375

    Cache writes are billed from input-token rates; cache hits are billed at a discounted read rate.